<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/d8c9faa2c0f84d1fa28a2ffac2da905f&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/d8c9faa2c0f84d1fa28a2ffac2da905f-87767df55599c7cd.gif</thumbnail_url><duration>406.64</duration><title>Improving Architectural Renders with Gemini AI 🎨</title><description>In this Loom I show how I use Google Gemini to improve the look of my Corona architectural renderings. I start with a 6k by 4k image, clip the exact areas I want to change, and paste them into Gemini with detailed instructions, like improving the people and changing a red car to white. After Gemini downloads the edits, I mask and feather them in Photoshop to keep it non destructive and seamless. I recommend doing changes in sections to avoid the AI going rogue.</description></oembed>